Re: [tip:perfcounters/core] perf_counter: x86: Fix call-chain support to use NMI-safe methods
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
- Subject: Re: [tip:perfcounters/core] perf_counter: x86: Fix call-chain support to use NMI-safe methods
- From: Ingo Molnar <mingo@xxxxxxx>
- Date: Mon, 15 Jun 2009 23:13:19 +0200
- Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, Jeremy Fitzhardinge <jeremy@xxxxxxxx>, Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxx>, mingo@xxxxxxxxxx, paulus@xxxxxxxxx, acme@xxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, a.p.zijlstra@xxxxxxxxx, penberg@xxxxxxxxxxxxxx, vegard.nossum@xxxxxxxxx, efault@xxxxxx, npiggin@xxxxxxx, tglx@xxxxxxxxxxxxx, linux-tip-commits@xxxxxxxxxxxxxxx
- In-reply-to: <4A36B746.4050001@xxxxxxxxx>
- References: <alpine.LFD.2.01.0906151029160.3305@xxxxxxxxxxxxxxxxxxxxx> <20090615180527.GB4201@Krystal> <alpine.LFD.2.01.0906151125320.6276@xxxxxxxxxxxxxxxxxxxxx> <20090615183649.GA16999@xxxxxxx> <alpine.LFD.2.01.0906151152170.6276@xxxxxxxxxxxxxxxxxxxxx> <4A36ABB5.1040109@xxxxxxxx> <alpine.LFD.2.01.0906151326170.6276@xxxxxxxxxxxxxxxxxxxxx> <4A36B238.5020203@xxxxxxxxx> <20090615205911.GC24554@xxxxxxx> <4A36B746.4050001@xxxxxxxxx>
- User-agent: Mutt/1.5.18 (2008-05-17)
* H. Peter Anvin <hpa@xxxxxxxxx> wrote:
> Ingo Molnar wrote:
> >
> > hm, does this really work? Using sysret there would be quite
> > tempting. Does anyone know the rough cycle count difference between
> > IRET and SYSRET on contemporary hardware?
> >
> > Also, is SYSRET NMI-invariant? If yes then this would be a quite
> > clean all-around solution: on modern hw we'd standardize on doing
> > SYSRET from pretty much all the contexts. We'd get a nice speedup
> > and also the NMI nested pagefaults fix.
> >
> > Oh, compat mode. Doesnt SYSRET on Intel CPUs have the problem of not
> > being able to switch back to 32-bit user-space?
> >
>
> Not sure. SYSRET/SYSEXIT are *not* general return to userspace
> solutions in either case; any kind of complex modes and they
> can't.
>
> And they are, of course, only applicable for returning to
> userspace. As such, I don't understand the "NMI invariant"
> comment.
Yeah - it makes no sense for the NMI return indeed, as the target
CS/SS is hardcoded indeed.
Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
[Index of Archives]
[Linux Stable Commits]
[Linux Stable Kernel]
[Linux Kernel]
[Linux USB Devel]
[Linux Video &Media]
[Linux Audio Users]
[Yosemite News]
[Linux SCSI]